SOCIALGYM 2.0: Simulator for Multi-Agent Social Robot Navigation in Shared Human Spaces
This provides a tool for social robot researchers to simulate and evaluate multi-agent navigation in shared human spaces, but it is incremental as it builds on existing MARL libraries and simulators.
The authors tackled the problem of simulating multi-agent social robot navigation in complex environments by developing SocialGym 2, a simulator that uses multi-agent reinforcement learning to create optimal navigation policies for multiple robots with diverse constraints, reporting benchmarks with various social navigation metrics.
We present SocialGym 2, a multi-agent navigation simulator for social robot research. Our simulator models multiple autonomous agents, replicating real-world dynamics in complex environments, including doorways, hallways, intersections, and roundabouts. Unlike traditional simulators that concentrate on single robots with basic kinematic constraints in open spaces, SocialGym 2 employs multi-agent reinforcement learning (MARL) to develop optimal navigation policies for multiple robots with diverse, dynamic constraints in complex environments. Built on the PettingZoo MARL library and Stable Baselines3 API, SocialGym 2 offers an accessible python interface that integrates with a navigation stack through ROS messaging. SocialGym 2 can be easily installed and is packaged in a docker container, and it provides the capability to swap and evaluate different MARL algorithms, as well as customize observation and reward functions. We also provide scripts to allow users to create their own environments and have conducted benchmarks using various social navigation algorithms, reporting a broad range of social navigation metrics. Projected hosted at: https://amrl.cs.utexas.edu/social_gym/index.html